In recent years, Deep Reinforcement Learning emerged as a promising approach for autonomous navigation of ground vehicles and has been utilized in various areas of navigation such as cruise control, lane changing, or obstacle avoidance. However, most research works either focus on providing an end-to-end solution training the whole system using Deep Reinforcement Learning or focus on one specific aspect such as local motion planning. This however, comes along with a number of problems such as catastrophic forgetfulness, inefficient navigation behavior, and non-optimal synchronization between different entities of the navigation stack. In this paper, we propose a holistic Deep Reinforcement Learning training approach in which the training procedure is involving all entities of the navigation stack. This should enhance the synchronization between- and understanding of all entities of the navigation stack and as a result, improve navigational performance. We trained several agents with a number of different observation spaces to study the impact of different input on the navigation behavior of the agent. In profound evaluations against multiple learning-based and classic model-based navigation approaches, our proposed agent could outperform the baselines in terms of efficiency and safety attaining shorter path lengths, less roundabout paths, and less collisions.
In recent years, mobile robot navigation approaches have become increasingly important due to various application areas ranging from healthcare to warehouse logistics. In particular, Deep Reinforcement Learning approaches have gained popularity for robot navigation but are not easily accessible to non-experts and complex to develop. In recent years, efforts have been made to make these sophisticated approaches accessible to a wider audience. In this paper, we present Arena-Web, a web-based development and evaluation suite for developing, training, and testing DRL-based navigation planners for various robotic platforms and scenarios. The interface is designed to be intuitive and engaging to appeal to non-experts and make the technology accessible to a wider audience. With Arena-Web and its interface, training and developing Deep Reinforcement Learning agents is simplified and made easy without a single line of code. The web-app is free to use and openly available under the link stated in the supplementary materials.
The rapid proliferation of non-cooperative spacecraft and space debris in orbit has precipitated a surging demand for on-orbit servicing and space debris removal at a scale that only autonomous missions can address, but the prerequisite autonomous navigation and flightpath planning to safely capture an unknown, non-cooperative, tumbling space object is an open problem. This requires algorithms for real-time, automated spacecraft feature recognition to pinpoint the locations of collision hazards (e.g. solar panels or antennas) and safe docking features (e.g. satellite bodies or thrusters) so safe, effective flightpaths can be planned. Prior work in this area reveals the performance of computer vision models are highly dependent on the training dataset and its coverage of scenarios visually similar to the real scenarios that occur in deployment. Hence, the algorithm may have degraded performance under certain lighting conditions even when the rendezvous maneuver conditions of the chaser to the target spacecraft are the same. This work delves into how humans perform these tasks through a survey of how aerospace engineering students experienced with spacecraft shapes and components recognize features of the three spacecraft: Landsat, Envisat, Anik, and the orbiter Mir. The survey reveals that the most common patterns in the human detection process were to consider the shape and texture of the features: antennas, solar panels, thrusters, and satellite bodies. This work introduces a novel algorithm SpaceYOLO, which fuses a state-of-the-art object detector YOLOv5 with a separate neural network based on these human-inspired decision processes exploiting shape and texture. Performance in autonomous spacecraft detection of SpaceYOLO is compared to ordinary YOLOv5 in hardware-in-the-loop experiments under different lighting and chaser maneuver conditions at the ORION Laboratory at Florida Tech.
To achieve optimal robot behavior in dynamic scenarios we need to consider complex dynamics in a predictive manner. In the vehicle dynamics community, it is well know that to achieve time-optimal driving on low surface, the vehicle should utilize drifting. Hence many authors have devised rules to split circuits and employ drifting on some segments. These rules are suboptimal and do not generalize to arbitrary circuit shapes (e.g., S-like curves). So, the question "When to go into which mode and how to drive in it?" remains unanswered. To choose the suitable mode (discrete decision), the algorithm needs information about the feasibility of the continuous motion in that mode. This makes it a class of Task and Motion Planning (TAMP) problems, which are known to be hard to solve optimally in real-time. In the AI planning community, search methods are commonly used. However, they cannot be directly applied to TAMP problems due to the continuous component. Here, we present a search-based method that effectively solves this problem and efficiently searches in a highly dimensional state space with nonlinear and unstable dynamics. The space of the possible trajectories is explored by sampling different combinations of motion primitives guided by the search. Our approach allows to use multiple locally approximated models to generate motion primitives (e.g., learned models of drifting) and effectively simplify the problem without losing accuracy. The algorithm performance is evaluated in simulated driving on a mixed-track with segments of different curvatures (right and left). Our code is available at https://git.io/JenvB
Autonomous navigation and path-planning around non-cooperative space objects is an enabling technology for on-orbit servicing and space debris removal systems. The navigation task includes the determination of target object motion, the identification of target object features suitable for grasping, and the identification of collision hazards and other keep-out zones. Given this knowledge, chaser spacecraft can be guided towards capture locations without damaging the target object or without unduly the operations of a servicing target by covering up solar arrays or communication antennas. One way to autonomously achieve target identification, characterization and feature recognition is by use of artificial intelligence algorithms. This paper discusses how the combination of cameras and machine learning algorithms can achieve the relative navigation task. The performance of two deep learning-based object detection algorithms, Faster Region-based Convolutional Neural Networks (R-CNN) and You Only Look Once (YOLOv5), is tested using experimental data obtained in formation flight simulations in the ORION Lab at Florida Institute of Technology. The simulation scenarios vary the yaw motion of the target object, the chaser approach trajectory, and the lighting conditions in order to test the algorithms in a wide range of realistic and performance limiting situations. The data analyzed include the mean average precision metrics in order to compare the performance of the object detectors. The paper discusses the path to implementing the feature recognition algorithms and towards integrating them into the spacecraft Guidance Navigation and Control system.
Self-driving vehicles rely on urban street maps for autonomous navigation. In this paper, we introduce Pix2Map, a method for inferring urban street map topology directly from ego-view images, as needed to continually update and expand existing maps. This is a challenging task, as we need to infer a complex urban road topology directly from raw image data. The main insight of this paper is that this problem can be posed as cross-modal retrieval by learning a joint, cross-modal embedding space for images and existing maps, represented as discrete graphs that encode the topological layout of the visual surroundings. We conduct our experimental evaluation using the Argoverse dataset and show that it is indeed possible to accurately retrieve street maps corresponding to both seen and unseen roads solely from image data. Moreover, we show that our retrieved maps can be used to update or expand existing maps and even show proof-of-concept results for visual localization and image retrieval from spatial graphs.
Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-the-art (SOTA) baselines. The demonstration video (https://www.youtube.com/watch?v=aqJCHcsj4w0) and the source code (https://github.com/OscarHuangWind/DRL-Transformer-SimtoReal-Navigation) are also provided.
Autonomous underwater vehicles (AUVs) are regularly used for deep ocean applications. Commonly, the autonomous navigation task is carried out by a fusion between two sensors: the inertial navigation system and the Doppler velocity log (DVL). The DVL operates by transmitting four acoustic beams to the sea floor, and once reflected back, the AUV velocity vector can be estimated. However, in real-life scenarios, such as an uneven seabed, sea creatures blocking the DVL's view and, roll/pitch maneuvers, the acoustic beams' reflection is resulting in a scenario known as DVL outage. Consequently, a velocity update is not available to bind the inertial solution drift. To cope with such situations, in this paper, we leverage our BeamsNet framework and propose a Set-Transformer-based BeamsNet (ST-BeamsNet) that utilizes inertial data readings and previous DVL velocity measurements to regress the current AUV velocity in case of a complete DVL outage. The proposed approach was evaluated using data from experiments held in the Mediterranean Sea with the Snapir AUV and was compared to a moving average (MA) estimator. Our ST-BeamsNet estimated the AUV velocity vector with an 8.547% speed error, which is 26% better than the MA approach.
Algorithmic solutions for multi-object tracking (MOT) are a key enabler for applications in autonomous navigation and applied ocean sciences. State-of-the-art MOT methods fully rely on a statistical model and typically use preprocessed sensor data as measurements. In particular, measurements are produced by a detector that extracts potential object locations from the raw sensor data collected for a discrete time step. This preparatory processing step reduces data flow and computational complexity but may result in a loss of information. State-of-the-art Bayesian MOT methods that are based on belief propagation (BP) systematically exploit graph structures of the statistical model to reduce computational complexity and improve scalability. However, as a fully model-based approach, BP can only provide suboptimal estimates when there is a mismatch between the statistical model and the true data-generating process. Existing BP-based MOT methods can further only make use of preprocessed measurements. In this paper, we introduce a variant of BP that combines model-based with data-driven MOT. The proposed neural enhanced belief propagation (NEBP) method complements the statistical model of BP by information learned from raw sensor data. This approach conjectures that the learned information can reduce model mismatch and thus improve data association and false alarm rejection. Our NEBP method improves tracking performance compared to model-based methods. At the same time, it inherits the advantages of BP-based MOT, i.e., it scales only quadratically in the number of objects, and it can thus generate and maintain a large number of object tracks. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it has state-of-the-art performance.
6D object pose estimation has been a research topic in the field of computer vision and robotics. Many modern world applications like robot grasping, manipulation, autonomous navigation etc, require the correct pose of objects present in a scene to perform their specific task. It becomes even harder when the objects are placed in a cluttered scene and the level of occlusion is high. Prior works have tried to overcome this problem but could not achieve accuracy that can be considered reliable in real-world applications. In this paper, we present an architecture that, unlike prior work, is context-aware. It utilizes the context information available to us about the objects. Our proposed architecture treats the objects separately according to their types i.e; symmetric and non-symmetric. A deeper estimator and refiner network pair is used for non-symmetric objects as compared to symmetric due to their intrinsic differences. Our experiments show an enhancement in the accuracy of about 3.2% over the LineMOD dataset, which is considered a benchmark for pose estimation in the occluded and cluttered scenes, against the prior state-of-the-art DenseFusion. Our results also show that the inference time we got is sufficient for real-time usage.
Event cameras detect changes in per-pixel intensity to generate asynchronous `event streams'. They offer great potential for accurate semantic map retrieval in real-time autonomous systems owing to their much higher temporal resolution and high dynamic range (HDR) compared to conventional cameras. However, existing implementations for event-based segmentation suffer from sub-optimal performance since these temporally dense events only measure the varying component of a visual signal, limiting their ability to encode dense spatial context compared to frames. To address this issue, we propose a hybrid end-to-end learning framework HALSIE, utilizing three key concepts to reduce inference cost by up to $20\times$ versus prior art while retaining similar performance: First, a simple and efficient cross-domain learning scheme to extract complementary spatio-temporal embeddings from both frames and events. Second, a specially designed dual-encoder scheme with Spiking Neural Network (SNN) and Artificial Neural Network (ANN) branches to minimize latency while retaining cross-domain feature aggregation. Third, a multi-scale cue mixer to model rich representations of the fused embeddings. These qualities of HALSIE allow for a very lightweight architecture achieving state-of-the-art segmentation performance on DDD-17, MVSEC, and DSEC-Semantic datasets with up to $33\times$ higher parameter efficiency and favorable inference cost (17.9mJ per cycle). Our ablation study also brings new insights into effective design choices that can prove beneficial for research across other vision tasks.
Laser scanning can provide timely assessments of mine sites despite adverse challenges in the operational environment. Although there are several published articles on laser scanning, there is a need to review them in the context of underground mining applications. To this end, a holistic review of laser scanning is presented including progress in 3D scanning systems, data capture/processing techniques and primary applications in underground mines. Laser scanning technology has advanced significantly in terms of mobility and mapping, but there are constraints in coherent and consistent data collection at certain mines due to feature deficiency, dynamics, and environmental influences such as dust and water. Studies suggest that laser scanning has matured over the years for change detection, clearance measurements and structure mapping applications. However, there is scope for improvements in lithology identification, surface parameter measurements, logistic tracking and autonomous navigation. Laser scanning has the potential to provide real-time solutions but the lack of infrastructure in underground mines for data transfer, geodetic networking and processing capacity remain limiting factors. Nevertheless, laser scanners are becoming an integral part of mine automation thanks to their affordability, accuracy and mobility, which should support their widespread usage in years to come.
Learning agents can optimize standard autonomous navigation improving flexibility, efficiency, and computational cost of the system by adopting a wide variety of approaches. This work introduces the \textit{PIC4rl-gym}, a fundamental modular framework to enhance navigation and learning research by mixing ROS2 and Gazebo, the standard tools of the robotics community, with Deep Reinforcement Learning (DRL). The paper describes the whole structure of the PIC4rl-gym, which fully integrates DRL agent's training and testing in several indoor and outdoor navigation scenarios and tasks. A modular approach is adopted to easily customize the simulation by selecting new platforms, sensors, or models. We demonstrate the potential of our novel gym by benchmarking the resulting policies, trained for different navigation tasks, with a complete set of metrics.
This paper describes how advanced deep learning based computer vision algorithms are applied to enable real-time on-board sensor processing for small UAVs. Four use cases are considered: target detection, classification and localization, road segmentation for autonomous navigation in GNSS-denied zones, human body segmentation, and human action recognition. All algorithms have been developed using state-of-the-art image processing methods based on deep neural networks. Acquisition campaigns have been carried out to collect custom datasets reflecting typical operational scenarios, where the peculiar point of view of a multi-rotor UAV is replicated. Algorithms architectures and trained models performances are reported, showing high levels of both accuracy and inference speed. Output examples and on-field videos are presented, demonstrating models operation when deployed on a GPU-powered commercial embedded device (NVIDIA Jetson Xavier) mounted on board of a custom quad-rotor, paving the way to enabling high level autonomy.
Interstellar objects (ISOs) represent a compelling and under-explored category of celestial bodies, providing physical laboratories to understand the formation of our solar system and probe the composition and properties of material formed in exoplanetary systems. In this work, we investigate existing approaches to designing successful flyby missions to ISOs, including a deep learning-driven guidance and control algorithm for ISOs traveling at velocities over 60 km/s. We have generated spacecraft trajectories to a series of synthetic representative ISOs, simulating a ground campaign to observe the target and resolve its state, thereby determining the cruise and close approach delta-Vs required for the encounter. We discuss the accessibility of and mission design to ISOs with varying characteristics, with special focuses on 1) state covariance estimation throughout the cruise, 2) handoffs from traditional navigation approaches to novel autonomous navigation for fast flyby regimes, and 3) overall recommendations about preparing for the future in situ exploration of these targets. The lessons learned also apply to the fast flyby of other small bodies, e.g., long-period comets and potentially hazardous asteroids, which also require tactical responses with similar characteristics.
Autonomous underwater vehicles (AUVs) are employed for marine applications and can operate in deep underwater environments beyond human reach. A standard solution for the autonomous navigation problem can be obtained by fusing the inertial navigation system and the Doppler velocity log sensor (DVL). The latter measures four beam velocities to estimate the vehicle's velocity vector. In real-world scenarios, the DVL may receive less than three beam velocities if the AUV operates in complex underwater environments. In such conditions, the vehicle's velocity vector could not be estimated leading to a navigation solution drift and in some situations the AUV is required to abort the mission and return to the surface. To circumvent such a situation, in this paper we propose a deep learning framework, LiBeamsNet, that utilizes the inertial data and the partial beam velocities to regress the missing beams in two missing beams scenarios. Once all the beams are obtained, the vehicle's velocity vector can be estimated. The approach performance was validated by sea experiments in the Mediterranean Sea. The results show up to 7.2% speed error in the vehicle's velocity vector estimation in a scenario that otherwise could not provide an estimate.
In this paper, we introduce a new computer vision task called nighttime dehaze-enhancement. This task aims to jointly perform dehazing and lightness enhancement. Our task fundamentally differs from nighttime dehazing -- our goal is to jointly dehaze and enhance scenes, while nighttime dehazing aims to dehaze scenes under a nighttime setting. In order to facilitate further research on this task, we release a new benchmark dataset called Reside-$\beta$ Night dataset, consisting of 4122 nighttime hazed images from 2061 scenes and 2061 ground truth images. Moreover, we also propose a new network called NDENet (Nighttime Dehaze-Enhancement Network), which jointly performs dehazing and low-light enhancement in an end-to-end manner. We evaluate our method on the proposed benchmark and achieve SSIM of 0.8962 and PSNR of 26.25. We also compare our network with other baseline networks on our benchmark to demonstrate the effectiveness of our approach. We believe that nighttime dehaze-enhancement is an essential task particularly for autonomous navigation applications, and hope that our work will open up new frontiers in research. Our dataset and code will be made publicly available upon acceptance of our paper.
Collision avoidance is a crucial task in vision-guided autonomous navigation. Solutions based on deep reinforcement learning (DRL) has become increasingly popular. In this work, we proposed several novel agent state and reward function designs to tackle two critical issues in DRL-based navigation solutions: 1) smoothness of the trained flight trajectories; and 2) model generalization to handle unseen environments. Formulated under a DRL framework, our model relies on margin reward and smoothness constraints to ensure UAVs fly smoothly while greatly reducing the chance of collision. The proposed smoothness reward minimizes a combination of first-order and second-order derivatives of flight trajectories, which can also drive the points to be evenly distributed, leading to stable flight speed. To enhance the agent's capability of handling new unseen environments, two practical setups are proposed to improve the invariance of both the state and reward function when deploying in different scenes. Experiments demonstrate the effectiveness of our overall design and individual components.
Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches lack safety guarantees; and learned navigation systems may not generalize well to unseen environments. Despite a variety of recent learning techniques to tackle these challenges in general, a lack of an open-source benchmark and reproducible learning methods specifically for autonomous navigation makes it difficult for roboticists to choose what learning methods to use for their mobile robots and for learning researchers to identify current shortcomings of general learning methods for autonomous navigation. In this paper, we identify four major desiderata of applying deep RL approaches for autonomous navigation: (D1) reasoning under uncertainty, (D2) safety, (D3) learning from limited trial-and-error data, and (D4) generalization to diverse and novel environments. Then, we explore four major classes of learning techniques with the purpose of achieving one or more of the four desiderata: memory-based neural network architectures (D1), safe RL (D2), model-based RL (D2, D3), and domain randomization (D4). By deploying these learning techniques in a new open-source large-scale navigation benchmark and real-world environments, we perform a comprehensive study aimed at establishing to what extent can these techniques achieve these desiderata for RL-based navigation systems.
The purpose of navigation is to determine the position, velocity, and orientation of manned and autonomous platforms, humans, and animals. Obtaining accurate navigation commonly requires fusion between several sensors, such as inertial sensors and global navigation satellite systems, in a model-based, nonlinear estimation framework. Recently, data-driven approaches applied in various fields show state-of-the-art performance, compared to model-based methods. In this paper we review multidisciplinary, data-driven based navigation algorithms developed and experimentally proven at the Autonomous Navigation and Sensor Fusion Lab (ANSFL) including algorithms suitable for human and animal applications, varied autonomous platforms, and multi-purpose navigation and fusion approaches